Songxiang Liu

Wen-Chin Huang, Lester Phillip Violeta, Songxiang Liu et al.

We present the latest iteration of the voice conversion challenge (VCC) series, a bi-annual scientific event aiming to compare and understand different voice conversion (VC) systems based on a common dataset. This year we shifted our focus to singing voice conversion (SVC), thus named the challenge the Singing Voice Conversion Challenge (SVCC). A new database was constructed for two tasks, namely in-domain and cross-domain SVC. The challenge was run for two months, and in total we received 26 submissions, including 2 baselines. Through a large-scale crowd-sourced listening test, we observed that for both tasks, although human-level naturalness was achieved by the top system, no team was able to obtain a similarity score as high as the target speakers. Also, as expected, cross-domain SVC is harder than in-domain SVC, especially in the similarity aspect. We also investigated whether existing objective measurements were able to predict perceptual performance, and found that only few of them could reach a significant correlation.

Dongchao Yang, Rongjie Huang, Yuanyuan Wang et al.

Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into either Auto-regressive (AR) based (\textit{e.g.}, VALL-E) or Non-auto-regressive (NAR) based models (\textit{e.g.}, NaturalSpeech 2/3). Although these works demonstrate good performance, they still have potential weaknesses. For instance, AR-based models are plagued by unstable generation quality and slow generation speed; meanwhile, some NAR-based models need phoneme-level duration alignment information, thereby increasing the complexity of data pre-processing, model design, and loss design. In this work, we build upon our previous publication by implementing a simple and efficient non-autoregressive (NAR) TTS framework, termed SimpleSpeech 2. SimpleSpeech 2 effectively combines the strengths of both autoregressive (AR) and non-autoregressive (NAR) methods, offering the following key advantages: (1) simplified data preparation; (2) straightforward model and loss design; and (3) stable, high-quality generation performance with fast inference speed. Compared to our previous publication, we present ({\romannumeral1}) a detailed analysis of the influence of speech tokenizer and noisy label for TTS performance; ({\romannumeral2}) four distinct types of sentence duration predictors; ({\romannumeral3}) a novel flow-based scalar latent transformer diffusion model. With these improvement, we show a significant improvement in generation performance and generation speed compared to our previous work and other state-of-the-art (SOTA) large-scale TTS models. Furthermore, we show that SimpleSpeech 2 can be seamlessly extended to multilingual TTS by training it on multilingual speech datasets. Demos are available on: {https://dongchaoyang.top/SimpleSpeech2\_demo/}.

KimiTeam, Ding Ding, Zeqian Ju et al.

We present Kimi-Audio, an open-source audio foundation model that excels in audio understanding, generation, and conversation. We detail the practices in building Kimi-Audio, including model architecture, data curation, training recipe, inference deployment, and evaluation. Specifically, we leverage a 12.5Hz audio tokenizer, design a novel LLM-based architecture with continuous features as input and discrete tokens as output, and develop a chunk-wise streaming detokenizer based on flow matching. We curate a pre-training dataset that consists of more than 13 million hours of audio data covering a wide range of modalities including speech, sound, and music, and build a pipeline to construct high-quality and diverse post-training data. Initialized from a pre-trained LLM, Kimi-Audio is continual pre-trained on both audio and text data with several carefully designed tasks, and then fine-tuned to support a diverse of audio-related tasks. Extensive evaluation shows that Kimi-Audio achieves state-of-the-art performance on a range of audio benchmarks including speech recognition, audio understanding, audio question answering, and speech conversation. We release the codes, model checkpoints, as well as the evaluation toolkits in https://github.com/MoonshotAI/Kimi-Audio.

Xinsheng Wang, Mingqi Jiang, Ziyang Ma et al.

Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.

Meituan LongCat Team, Bairui Wang, Bayan et al.

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

Yueqian Wang, Songxiang Liu, Disong Wang et al.

Recent advances in video multimodal large language models (Video MLLMs) have significantly enhanced video understanding and multi-modal interaction capabilities. While most existing systems operate in a turn-based manner where the model can only reply after user turns, proactively deciding when to reply during video playback presents a promising yet challenging direction for real-time applications. In this work, we propose a novel text-to-text approach to proactive interaction, where the model autonomously determines whether to respond or remain silent at each turn based on dialogue history and visual context up to current frame of an streaming video. To overcome difficulties in previous methods such as manually tuning response decision thresholds and annotating precise reply times, we introduce a multi-turn RL based training method that encourages timely and accurate responses without requiring precise response time annotations. We train our model MMDuet2 on a dataset of 52k videos with two types of dialogues via SFT and RL. Experimental results demonstrate that MMDuet2 outperforms existing proactive Video MLLM baselines in response timing and quality, achieving state-of-the-art performance on the ProactiveVideoQA benchmark.

Dongchao Yang, Songxiang Liu, Disong Wang et al.

Recent advances in Omni models have enabled unified multimodal perception and generation. However, most existing systems still exhibit rigid reasoning behaviors, either overthinking simple problems or failing to reason when necessary. To address this limitation, we propose Omni-AutoThink, a novel adaptive reasoning framework that dynamically adjusts the model's reasoning depth according to task difficulty. Our framework comprises two stages: (1) an Adaptive Supervised Fine-Tuning (Adaptive SFT) stage, which endows the Omni model with fundamental reasoning capability using large-scale reasoning-augmented data, and (2) an Adaptive Reinforcement Learning (Adaptive GRPO) stage, which optimizes reasoning behaviors based on task complexity and reward feedback. We further construct a comprehensive adaptive reasoning benchmark that spans text-only, text-audio, text-visual, and text-audio-visual modalities, providing both training and evaluation splits for multimodal reasoning assessment. Experimental results demonstrate that our proposed framework significantly improves adaptive reasoning performance compared to previous baselines. All benchmark data and code will be publicly released.

Ziteng Wang, Yujie He, Guanliang Li et al.

Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated impressive performance on standard visual reasoning benchmarks. However, there is growing concern that these models rely excessively on linguistic shortcuts rather than genuine visual grounding, a phenomenon we term Text Bias. In this paper, we investigate the fundamental tension between visual perception and linguistic priors. We decouple the sources of this bias into two dimensions: Internal Corpus Bias, stemming from statistical correlations in pretraining, and External Instruction Bias, arising from the alignment-induced tendency toward sycophancy. To quantify this effect, we introduce V-FAT (Visual Fidelity Against Text-bias), a diagnostic benchmark comprising 4,026 VQA instances across six semantic domains. V-FAT employs a Three-Level Evaluation Framework that systematically increases the conflict between visual evidence and textual information: (L1) internal bias from atypical images, (L2) external bias from misleading instructions, and (L3) synergistic bias where both coincide. We introduce the Visual Robustness Score (VRS), a metric designed to penalize "lucky" linguistic guesses and reward true visual fidelity. Our evaluation of 12 frontier MLLMs reveals that while models excel in existing benchmarks, they experience significant visual collapse under high linguistic dominance.

Disong Wang, Songxiang Liu, Xixin Wu et al.

Dysarthric speech reconstruction (DSR), which aims to improve the quality of dysarthric speech, remains a challenge, not only because we need to restore the speech to be normal, but also must preserve the speaker's identity. The speaker representation extracted by the speaker encoder (SE) optimized for speaker verification has been explored to control the speaker identity. However, the SE may not be able to fully capture the characteristics of dysarthric speakers that are previously unseen. To address this research problem, we propose a novel multi-task learning strategy, i.e., adversarial speaker adaptation (ASA). The primary task of ASA fine-tunes the SE with the speech of the target dysarthric speaker to effectively capture identity-related information, and the secondary task applies adversarial training to avoid the incorporation of abnormal speaking patterns into the reconstructed speech, by regularizing the distribution of reconstructed speech to be close to that of reference speech with high quality. Experiments show that the proposed approach can achieve enhanced speaker similarity and comparable speech naturalness with a strong baseline approach. Compared with dysarthric speech, the reconstructed speech achieves 22.3% and 31.5% absolute word error rate reduction for speakers with moderate and moderate-severe dysarthria respectively. Our demo page is released here: https://wendison.github.io/ASA-DSR-demo/

Songxiang Liu, Dan Su, Dong Yu

Denoising diffusion probabilistic models (DDPMs) are expressive generative models that have been used to solve a variety of speech synthesis problems. However, because of their high sampling costs, DDPMs are difficult to use in real-time speech processing applications. In this paper, we introduce DiffGAN-TTS, a novel DDPM-based text-to-speech (TTS) model achieving high-fidelity and efficient speech synthesis. DiffGAN-TTS is based on denoising diffusion generative adversarial networks (GANs), which adopt an adversarially-trained expressive model to approximate the denoising distribution. We show with multi-speaker TTS experiments that DiffGAN-TTS can generate high-fidelity speech samples within only 4 denoising steps. We present an active shallow diffusion mechanism to further speed up inference. A two-stage training scheme is proposed, with a basic TTS acoustic model trained at stage one providing valuable prior information for a DDPM trained at stage two. Our experiments show that DiffGAN-TTS can achieve high synthesis performance with only 1 denoising step.

Songxiang Liu, Dan Su, Dong Yu

The task of few-shot style transfer for voice cloning in text-to-speech (TTS) synthesis aims at transferring speaking styles of an arbitrary source speaker to a target speaker's voice using very limited amount of neutral data. This is a very challenging task since the learning algorithm needs to deal with few-shot voice cloning and speaker-prosody disentanglement at the same time. Accelerating the adaptation process for a new target speaker is of importance in real-world applications, but even more challenging. In this paper, we approach to the hard fast few-shot style transfer for voice cloning task using meta learning. We investigate the model-agnostic meta-learning (MAML) algorithm and meta-transfer a pre-trained multi-speaker and multi-prosody base TTS model to be highly sensitive for adaptation with few samples. Domain adversarial training mechanism and orthogonal constraint are adopted to disentangle speaker and prosody representations for effective cross-speaker style transfer. Experimental results show that the proposed approach is able to conduct fast voice cloning using only 5 samples (around 12 second speech data) from a target speaker, with only 100 adaptation steps. Audio samples are available online.

Songxiang Liu, Shan Yang, Dan Su et al.

Cross-speaker style transfer (CSST) in text-to-speech (TTS) synthesis aims at transferring a speaking style to the synthesised speech in a target speaker's voice. Most previous CSST approaches rely on expensive high-quality data carrying desired speaking style during training and require a reference utterance to obtain speaking style descriptors as conditioning on the generation of a new sentence. This work presents Referee, a robust reference-free CSST approach for expressive TTS, which fully leverages low-quality data to learn speaking styles from text. Referee is built by cascading a text-to-style (T2S) model with a style-to-wave (S2W) model. Phonetic PosteriorGram (PPG), phoneme-level pitch and energy contours are adopted as fine-grained speaking style descriptors, which are predicted from text using the T2S model. A novel pretrain-refinement method is adopted to learn a robust T2S model by only using readily accessible low-quality data. The S2W model is trained with high-quality target data, which is adopted to effectively aggregate style descriptors and generate high-fidelity speech in the target speaker's voice. Experimental results are presented, showing that Referee outperforms a global-style-token (GST)-based baseline approach in CSST.

Lingyun Feng, Jianwei Yu, Deng Cai et al.

Language understanding in speech-based systems have attracted much attention in recent years with the growing demand for voice interface applications. However, the robustness of natural language understanding (NLU) systems to errors introduced by automatic speech recognition (ASR) is under-examined. %To facilitate the research on ASR-robust general language understanding, In this paper, we propose ASR-GLUE benchmark, a new collection of 6 different NLU tasks for evaluating the performance of models under ASR error across 3 different levels of background noise and 6 speakers with various voice characteristics. Based on the proposed benchmark, we systematically investigate the effect of ASR error on NLU tasks in terms of noise intensity, error type and speaker variants. We further purpose two ways, correction-based method and data augmentation-based method to improve robustness of the NLU systems. Extensive experimental results and analysises show that the proposed methods are effective to some extent, but still far from human performance, demonstrating that NLU under ASR error is still very challenging and requires further research.

Songxiang Liu, Yuewen Cao, Dan Su et al.

Singing voice conversion (SVC) is one promising technique which can enrich the way of human-computer interaction by endowing a computer the ability to produce high-fidelity and expressive singing voice. In this paper, we propose DiffSVC, an SVC system based on denoising diffusion probabilistic model. DiffSVC uses phonetic posteriorgrams (PPGs) as content features. A denoising module is trained in DiffSVC, which takes destroyed mel spectrogram produced by the diffusion/forward process and its corresponding step information as input to predict the added Gaussian noise. We use PPGs, fundamental frequency features and loudness features as auxiliary input to assist the denoising process. Experiments show that DiffSVC can achieve superior conversion performance in terms of naturalness and voice similarity to current state-of-the-art SVC approaches.

Peng Liu, Yuewen Cao, Songxiang Liu et al.

This paper proposes VARA-TTS, a non-autoregressive (non-AR) text-to-speech (TTS) model using a very deep Variational Autoencoder (VDVAE) with Residual Attention mechanism, which refines the textual-to-acoustic alignment layer-wisely. Hierarchical latent variables with different temporal resolutions from the VDVAE are used as queries for residual attention module. By leveraging the coarse global alignment from previous attention layer as an extra input, the following attention layer can produce a refined version of alignment. This amortizes the burden of learning the textual-to-acoustic alignment among multiple attention layers and outperforms the use of only a single attention layer in robustness. An utterance-level speaking speed factor is computed by a jointly-trained speaking speed predictor, which takes the mean-pooled latent variables of the coarsest layer as input, to determine number of acoustic frames at inference. Experimental results show that VARA-TTS achieves slightly inferior speech quality to an AR counterpart Tacotron 2 but an order-of-magnitude speed-up at inference; and outperforms an analogous non-AR model, BVAE-TTS, in terms of speech quality.

Disong Wang, Songxiang Liu, Lifa Sun et al.

Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody while maintaining speaker identity. To address this issue, we propose a VC system with explicit prosodic modelling and deep speaker embedding (DSE) learning. First, a speech-encoder strives to extract robust phoneme embeddings from atypical speech. Second, a prosody corrector takes in phoneme embeddings to infer typical phoneme duration and pitch values. Third, a conversion model takes phoneme embeddings and typical prosody features as inputs to generate the converted speech, conditioned on the target DSE that is learned via speaker encoder or speaker adaptation. Extensive experiments demonstrate that speaker adaptation can achieve higher speaker similarity, and the speaker encoder based conversion model can greatly reduce dysarthric and non-native pronunciation patterns with improved speech intelligibility. A comparison of speech recognition results between the original dysarthric speech and converted speech show that absolute reduction of 47.6% character error rate (CER) and 29.3% word error rate (WER) can be achieved.

Songxiang Liu, Yuewen Cao, Disong Wang et al.

This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach, which utilizes text supervision during training. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. During the training stage, an encoder-decoder-based hybrid connectionist-temporal-classification-attention (CTC-attention) phoneme recognizer is trained, whose encoder has a bottle-neck layer. A BNE is obtained from the phoneme recognizer and is utilized to extract speaker-independent, dense and rich spoken content representations from spectral features. Then a multi-speaker location-relative attention based seq2seq synthesis model is trained to reconstruct spectral features from the bottle-neck features, conditioning on speaker representations for speaker identity control in the generated speech. To mitigate the difficulties of using seq2seq models to align long sequences, we down-sample the input spectral feature along the temporal dimension and equip the synthesis model with a discretized mixture of logistic (MoL) attention mechanism. Since the phoneme recognizer is trained with large speech recognition data corpus, the proposed approach can conduct any-to-many voice conversion. Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity. Ablation studies are conducted to confirm the effectiveness of feature selection and model design strategies in the proposed approach. The proposed VC approach can readily be extended to support any-to-any VC (also known as one/few-shot VC), and achieve high performance according to objective and subjective evaluations.

Haibin Wu, Songxiang Liu, Helen Meng et al.

Various forefront countermeasure methods for automatic speaker verification (ASV) with considerable performance in anti-spoofing are proposed in the ASVspoof 2019 challenge. However, previous work has shown that countermeasure models are vulnerable to adversarial examples indistinguishable from natural data. A good countermeasure model should not only be robust against spoofing audio, including synthetic, converted, and replayed audios; but counteract deliberately generated examples by malicious adversaries. In this work, we introduce a passive defense method, spatial smoothing, and a proactive defense method, adversarial training, to mitigate the vulnerability of ASV spoofing countermeasure models against adversarial examples. This paper is among the first to use defense methods to improve the robustness of ASV spoofing countermeasure models under adversarial attacks. The experimental results show that these two defense methods positively help spoofing countermeasure models counter adversarial examples.

Lei Shi, Shijie Geng, Kai Shuang et al.

Multi-modality fusion technologies have greatly improved the performance of neural network-based Video Description/Caption, Visual Question Answering (VQA) and Audio Visual Scene-aware Dialog (AVSD) over the recent years. Most previous approaches only explore the last layers of multiple layer feature fusion while omitting the importance of intermediate layers. To solve the issue for the intermediate layers, we propose an efficient Quaternion Block Network (QBN) to learn interaction not only for the last layer but also for all intermediate layers simultaneously. In our proposed QBN, we use the holistic text features to guide the update of visual features. In the meantime, Hamilton quaternion products can efficiently perform information flow from higher layers to lower layers for both visual and text modalities. The evaluation results show our QBN improved the performance on VQA 2.0, even though using surpass large scale BERT or visual BERT pre-trained models. Extensive ablation study has been carried out to testify the influence of each proposed module in this study.

Songxiang Liu, Haibin Wu, Hung-yi Lee et al.

High-performance spoofing countermeasure systems for automatic speaker verification (ASV) have been proposed in the ASVspoof 2019 challenge. However, the robustness of such systems under adversarial attacks has not been studied yet. In this paper, we investigate the vulnerability of spoofing countermeasures for ASV under both white-box and black-box adversarial attacks with the fast gradient sign method (FGSM) and the projected gradient descent (PGD) method. We implement high-performing countermeasure models in the ASVspoof 2019 challenge and conduct adversarial attacks on them. We compare performance of black-box attacks across spoofing countermeasure models with different network architectures and different amount of model parameters. The experimental results show that all implemented countermeasure models are vulnerable to FGSM and PGD attacks under the scenario of white-box attack. The more dangerous black-box attacks also prove to be effective by the experimental results.